Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    find

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     WhatsApp
    -0.07
    EditingController
    -0.07
    Photon
    -0.07
    �
    -0.07
    087
    -0.07
     veřejné
    -0.07
     práv
    -0.07
     emitter
    -0.06
    _click
    -0.06
    _Equals
    -0.06
    POSITIVE LOGITS
    .inter
    0.06
    ыџN
    0.06
     find
    0.06
     THAT
    0.06
    $PostalCodesNL
    0.06
    	mock
    0.05
    итися
    0.05
    cont
    0.05
    ند
    0.05
     faint
    0.05
    Act Density 0.032%

    No Known Activations